Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add DVNghiem/FlowDeck --skill repo-memory-graphgit clone --depth 1 https://github.com/DVNghiem/FlowDeckWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dvnghiem/flowdeck/repo-memory-graph)<a href="https://agentmods.dev/skills/dvnghiem/flowdeck/repo-memory-graph"><img src="https://agentmods.dev/badge/skills/dvnghiem/flowdeck/repo-memory-graph.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.00453 |
| Opus 5 | $0.00015 | $0.00227 |
| Sonnet 5 | $0.00006 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
repo-memory-graph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Repo Memory Graph
The Repo Memory Graph is FlowDeck's long-term knowledge store about this specific codebase. It persists in ~/.fd-plan/<slug>/.codebase/MEMORY.json and grows over time.
What Gets Stored
- Modules: files, their type (service/api/schema/config), owner, tags
- Dependencies: which modules import or call which others
- Conventions: patterns used in this repo (naming, error handling, auth flow)
- Bug history: which modules have had recurring issues
- Ownership: who owns what (from git blame, CODEOWNERS, or explicit annotation)
When to Update
Update the graph:
- After
/fd-taskmaps the codebase during init - When onboarding a new module
- When a bug fix reveals a recurring pattern (add to
bug_history) - When a refactor changes module ownership
Usage with repo-memory tool
// Write a node
{ "action": "write_node", "node_id": "auth-service", "node": {
"type": "service", "path": "src/services/auth.ts",
"owner": "security-team", "tags": ["auth", "jwt"],
"dependencies": ["user-model", "token-store"],
"dependents": ["api-gateway", "session-handler"],
"bug_history": ["jwt-expiry-bug-2024-03"],
"conventions": ["always validate token before processing"]
}}
// Query by owner
{ "action": "query", "query": { "owner": "security-team" } }
How Agents Use This
- Impact Radar: walks the dependency graph to find affected modules
- Blast Radius: traverses dependents to map downstream risk
- Regression Prediction: uses bug_history to weight risk categories
- Architectural Constraint Guard: checks module boundaries before allowing edits
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 50 lines · 31 tokens per session scan A 54cc19af624b
repo-memory-graph is a skill published in the GitHub repository DVNghiem/FlowDeck (24 stars, last pushed 18d ago), licensed MIT. It adds 31 tokens to every session and 453 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
oh-my-opencode-slim
Configure and improve oh-my-opencode-slim for the current user. Use when users want to tune agents, models, prompts, custom agents, skills, MCPs, presets, or plugin behavior. Also use when recurring workflow friction suggests a safe config or prompt improvement.
clonedeps
Clone important project dependency source code into an ignored local workspace so OpenCode can inspect library internals. Use when the user asks to clone dependencies, inspect dependency/source internals, understand SDK/framework behavior from source, debug library implementation details, or make core dependency repos…
codemap
Generate comprehensive hierarchical codemaps for UNFAMILIAR repositories. Expensive operation - only use when explicitly asked for codebase documentation or initial repository mapping.
deepwork
High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
simplify
Simplifies code for clarity without changing behavior. Use for readability, maintainability, and complexity reduction after behavior is understood.